一作ICLR 2026Poster· Social Aspects / Trustworthy Machine Learning
Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
Renyang Liu · Guanlin Li · Tianwei Zhang · See-Kiong Ng
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Renyang Liu · Guanlin Li · Tianwei Zhang · See-Kiong Ng
Tingchao Fu · Wenkai Wang · Fanxiao Li · Huadong Zhang · Jinhong Zhang · Dayang Li · Yunyun Dong · Renyang Liu · Wei Zhou
Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updat...